Model Comparison

DeepSeek VL2 Tiny vs DeepSeek VL2 Small

DeepSeek VL2 Small significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

14 benchmarks

DeepSeek VL2 Tiny outperforms in 0 benchmarks, while DeepSeek VL2 Small is better at 14 benchmarks (AI2D, ChartQA, DocVQA, InfoVQA, MathVista, MMBench, MMBench-V1.1, MME, MMMU, MMStar, MMT-Bench, OCRBench, RealWorldQA, TextVQA).

DeepSeek VL2 Small significantly outperforms across most benchmarks.

Fri Apr 10 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Cost data unavailable.

Lowest available price from all providers
Fri Apr 10 2026 • llm-stats.com
DeepSeek
DeepSeek VL2 Tiny
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
DeepSeek
DeepSeek VL2 Small
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

13.0B diff

DeepSeek VL2 Small has 13.0B more parameters than DeepSeek VL2 Tiny, making it 433.3% larger.

DeepSeek
DeepSeek VL2 Tiny
3.0Bparameters
DeepSeek
DeepSeek VL2 Small
16.0Bparameters
3.0B
DeepSeek VL2 Tiny
16.0B
DeepSeek VL2 Small

Input Capabilities

Supported data types and modalities

Both DeepSeek VL2 Tiny and DeepSeek VL2 Small support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

DeepSeek VL2 Tiny

Text
Images
Audio
Video

DeepSeek VL2 Small

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under deepseek.

Both models share the same licensing terms, providing consistent usage rights.

DeepSeek VL2 Tiny

deepseek

Open weights

DeepSeek VL2 Small

deepseek

Open weights

Release Timeline

When each model was launched

Both models were released on 2024-12-13.

They likely represent similar generations of model development.

DeepSeek VL2 Tiny

Dec 13, 2024

1.3 years ago

DeepSeek VL2 Small

Dec 13, 2024

1.3 years ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

DeepSeek
DeepSeek
Higher AI2D score (80.0% vs 71.6%)
Higher ChartQA score (84.5% vs 81.0%)
Higher DocVQA score (92.3% vs 88.9%)
Higher InfoVQA score (75.8% vs 66.1%)
Higher MathVista score (60.7% vs 53.6%)
Higher MMBench score (80.3% vs 69.2%)
Higher MMBench-V1.1 score (79.3% vs 68.3%)
Higher MME score (21.2% vs 19.1%)
Higher MMMU score (48.0% vs 40.7%)
Higher MMStar score (57.0% vs 45.9%)
Higher MMT-Bench score (62.9% vs 53.2%)
Higher OCRBench score (83.4% vs 80.9%)
Higher RealWorldQA score (65.4% vs 64.2%)
Higher TextVQA score (83.4% vs 80.7%)

Detailed Comparison

AI Model Comparison Table
Feature
DeepSeek
DeepSeek VL2 Tiny
DeepSeek
DeepSeek VL2 Small

FAQ

Common questions about DeepSeek VL2 Tiny vs DeepSeek VL2 Small

DeepSeek VL2 Small significantly outperforms across most benchmarks. DeepSeek VL2 Tiny is made by DeepSeek and DeepSeek VL2 Small is made by DeepSeek. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
DeepSeek VL2 Tiny scores DocVQA: 88.9%, ChartQA: 81.0%, OCRBench: 80.9%, TextVQA: 80.7%, AI2D: 71.6%. DeepSeek VL2 Small scores DocVQA: 92.3%, ChartQA: 84.5%, OCRBench: 83.4%, TextVQA: 83.4%, MMBench: 80.3%.